Token导航 LogoToken导航TokenDH.com
待分类敏感数据github未标认证来源可访问许可证需确认审计异常

anti-detect-browser反检测浏览器

Agent Skill

anti-detect-browser 用于处理浏览器自动化、网页检查和页面信息提取,适合在 Codex、Claude、Cursor、Gemini CLI 中需要让 Agent 打开页面、读取网页或验证前端流程时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

244,725

周安装

10,181

GitHub Stars

公开资料未说明

下载量

81,886
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:anti-detect-browser(反检测浏览器)
来源仓库:https://github.com/antibrow/anti-detect-browser-skills
仓库路径:skills/anti-detect-browser
安装命令:
npx skills add https://github.com/antibrow/anti-detect-browser-skills --skill anti-detect-browser
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/antibrow/anti-detect-browser-skills --skill anti-detect-browser

简介

用于创建和管理具有真实设备指纹的浏览器实例,支持网页自动化与数据整理。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中进行多账户管理或前端流程验证。
  • 基于 Playwright API 启动 Chromium,每个实例拥有唯一且一致的数字身份。
  • 安装命令为 npx skills add https://github.com/antibrow/anti-detect-browser-skills --skill anti-detect-browser。
  • 使用前需确认权限范围及是否会触发联网或文件访问操作。

SKILL.md

Anti-Detect Browser SDK

Launch Chromium instances with real-device fingerprints via standard Playwright APIs. Each browser gets a unique, consistent digital identity - undetectable by anti-bot systems.

  • npm package: anti-detect-browser
  • Dashboard: https://antibrow.com
  • REST API base: https://antibrow.com/api/v1/
  • Documentation: https://antibrow.com/docs

When to use

  • Multi-account management - Run dozens of social media, e-commerce, or ad accounts on the same machine without linking. Each browser profile has its own fingerprint, cookies, and storage.
  • Web scraping & data collection - Rotate fingerprints across scraping sessions to avoid detection and fingerprint-IP correlation bans.
  • Ad verification & competitive intelligence - View ads and content as different user profiles across regions and device types.
  • Social media automation - Manage multiple accounts with persistent profiles that survive browser restarts.
  • E-commerce operations - Operate multiple seller/buyer accounts with fully isolated browser environments.
  • AI agent browser control - Run as an MCP server so AI agents (Claude, GPT, etc.) can launch, navigate, and interact with anti-detect browsers through tool calls.
  • QA & cross-environment testing - Test how your site behaves under different browser fingerprints, screen sizes, and device configurations.

Quick start

npm install anti-detect-browser
import { AntiDetectBrowser } from 'anti-detect-browser'

// Get your API key at https://antibrow.com
const ab = new AntiDetectBrowser({ key: 'your-api-key' })

const { browser, page } = await ab.launch({
  fingerprint: { tags: ['Windows 10', 'Chrome'] },
  profile: 'my-account-01',
  proxy: 'http://user:pass@host:port',
})

// Standard Playwright API from here — zero learning curve
await page.goto('https://example.com')
await browser.close()

Core concepts

Profiles — persistent browser identities

A profile saves cookies, localStorage, and session data across launches. Same profile name = same stored state next time.

// First launch — fresh session
const { page } = await ab.launch({ profile: 'shop-01' })
await page.goto('https://shop.example.com/login')
// ... login ...
await browser.close()

// Later — session restored, already logged in
const { page: p2 } = await ab.launch({ profile: 'shop-01' })
await p2.goto('https://shop.example.com/dashboard') // no login needed

Fingerprints — real device data from the cloud

Each launch fetches a real fingerprint collected from actual devices. Over 30 categories (Canvas, WebGL, Audio, Fonts, WebRTC, WebGPU, etc.) with 500+ individual parameters.

// Windows Chrome, version 130+
await ab.launch({
  fingerprint: { tags: ['Windows 10', 'Chrome'], minBrowserVersion: 130 },
})

// Mac Safari
await ab.launch({
  fingerprint: { tags: ['Apple Mac', 'Safari'] },
})

// Mobile Android
await ab.launch({
  fingerprint: { tags: ['Android', 'Mobile', 'Chrome'] },
})

Available filter tags: Microsoft Windows, Apple Mac, Android, Linux, iPad, iPhone, Edge, Chrome, Safari, Firefox, Desktop, Mobile, Windows 7, Windows 8, Windows 10

Visual identification — tell windows apart at a glance

When running many browsers simultaneously, each window gets a floating label, title prefix, and unique theme color.

await ab.launch({
  profile: 'twitter-main',
  label: '@myhandle',       // floating label + window title
  color: '#e74c3c',         // unique window border color
})

Proxy integration

Route each browser through a different proxy for geo-targeting or IP rotation.

await ab.launch({
  proxy: 'socks5://user:pass@us-proxy.example.com:1080',
  fingerprint: { tags: ['Windows 10', 'Chrome'] },
  profile: 'us-account',
})

Live View — watch headless browsers in real time

Monitor headless sessions from the https://antibrow.com dashboard. Useful for debugging AI agent actions or letting team members observe.

const { liveView } = await ab.launch({
  headless: true,
  liveView: true,
})

console.log('Watch live:', liveView.viewUrl)
// Share this URL — anyone with access can see the browser screen

Inject into existing Playwright setup

Already have Playwright scripts? Add fingerprints without changing your workflow.

import { chromium } from 'playwright'
import { applyFingerprint } from 'anti-detect-browser'

const browser = await chromium.launch()
const context = await browser.newContext()

await applyFingerprint(context, {
  key: 'your-api-key',
  fingerprint: { tags: ['Windows 10', 'Chrome'] },
  profile: 'my-profile',
})

const page = await context.newPage()
await page.goto('https://example.com')

MCP server mode — for AI agents

Run as an MCP server so AI agents can launch and control fingerprint browsers via tool calls.

{
  "mcpServers": {
    "anti-detect-browser": {
      "command": "npx",
      "args": ["anti-detect-browser", "--mcp"],
      "env": { "ANTI_DETECT_BROWSER_KEY": "your-api-key" }
    }
  }
}

Available tools:

ToolWhat it does
launch_browserStart a new fingerprint browser session
close_browserClose a running session
navigateGo to a URL
screenshotCapture the current screen
click / fillInteract with page elements
evaluateRun JavaScript on the page
get_contentExtract text from the page or a specific element
start_live_viewStream the browser screen to https://antibrow.com dashboard
stop_live_viewStop live streaming
list_sessionsList all running browser instances
list_profilesList all saved profiles

Workflow examples

Multi-account social media

const accounts = [
  { profile: 'twitter-1', label: '@brand_main', color: '#1DA1F2' },
  { profile: 'twitter-2', label: '@support', color: '#FF6B35' },
  { profile: 'twitter-3', label: '@personal', color: '#6C5CE7' },
]

for (const acct of accounts) {
  const { page } = await ab.launch({
    fingerprint: { tags: ['Windows 10', 'Chrome'] },
    proxy: getNextProxy(),
    ...acct,
  })
  await page.goto('https://twitter.com')
}

Scraping with fingerprint rotation

for (const url of urlsToScrape) {
  const { browser, page } = await ab.launch({
    fingerprint: { tags: ['Desktop', 'Chrome'], minBrowserVersion: 125 },
    proxy: rotateProxy(),
  })
  await page.goto(url)
  const data = await page.evaluate(() => document.body.innerText)
  saveData(url, data)
  await browser.close()
}

Headless monitoring with live view

const { page, liveView } = await ab.launch({
  headless: true,
  liveView: true,
  profile: 'price-monitor',
  fingerprint: { tags: ['Windows 10', 'Chrome'] },
})

// Share the live view URL with your team
console.log('Dashboard:', liveView.viewUrl)

while (true) {
  await page.goto('https://shop.example.com/product/123')
  const price = await page.textContent('.price')
  if (parseFloat(price) < targetPrice) notify(price)
  await page.waitForTimeout(60_000)
}

REST API

Base URL: https://antibrow.com/api/v1/ — all endpoints require Authorization: Bearer <api-key> header.

Fingerprints

MethodEndpointDescription
GET/fingerprints/fetchFetch a fingerprint matching filter criteria. Returns {dataUrl} — download the presigned URL for full fingerprint data.
GET/fingerprints/versionsList available browser versions

Query parameters for /fingerprints/fetch: tags, id, minBrowserVersion, maxBrowserVersion, minWidth, maxWidth, minHeight, maxHeight

Profiles

MethodEndpointDescription
GET/profilesList all profiles
POST/profilesCreate a new profile (server assigns a random fingerprint). Returns profile info including dataUrl for immediate fingerprint data download.
GET/profiles/:nameGet profile details with dataUrl for fingerprint data download
DELETE/profiles/:nameDelete a profile

POST /profiles request body:

{ "name": "my-profile", "tags": ["Windows 10", "Chrome"] }

POST /profiles response (201):

{
  "name": "my-profile",
  "tags": ["Windows 10", "Chrome"],
  "ua": "Mozilla/5.0 ...",
  "browserVersion": 131,
  "width": 1920,
  "height": 1080,
  "createdAt": "2025-01-01T00:00:00.000Z",
  "dataUrl": "https://r2.example.com/fingerprints/..."
}

The dataUrl is a presigned R2 URL (valid for 10 minutes) pointing to the full fingerprint JSON data (~9MB). Download it directly — no additional API call needed.

Get started

  1. Sign up at https://antibrow.com (free tier: 2 browser profiles)
  2. Get your API key from the dashboard
  3. npm install anti-detect-browser
  4. Launch your first anti-detect browser

Full documentation: https://antibrow.com/docs

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

35.46%
按下载量换算29,037

Claude

29.55%
按下载量换算24,197

Cursor

19.36%
按下载量换算15,853

Gemini CLI

10.03%
按下载量换算8,213

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

未通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills